CN117730265A - Method for detecting LiDAR point cloud data abnormality and related equipment - Google Patents
Method for detecting LiDAR point cloud data abnormality and related equipment Download PDFInfo
- Publication number
- CN117730265A CN117730265A CN202180100860.0A CN202180100860A CN117730265A CN 117730265 A CN117730265 A CN 117730265A CN 202180100860 A CN202180100860 A CN 202180100860A CN 117730265 A CN117730265 A CN 117730265A
- Authority
- CN
- China
- Prior art keywords
- position information
- data point
- determining
- target data
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000005856 abnormality Effects 0.000 title abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims abstract description 6
- 230000015654 memory Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 description 25
- 238000007781 pre-processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000008447 perception Effects 0.000 description 8
- 238000013461 design Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000000098 azimuthal photoelectron diffraction Methods 0.000 description 1
- 230000032823 cell division Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/42—Simultaneous measurement of distance and other co-ordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4808—Evaluating distance, position or velocity data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/495—Counter-measures or counter-counter-measures using electronic or electro-optical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/497—Means for monitoring or calibrating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
- G01S17/10—Systems determining position data of a target for measuring distance only using transmission of interrupted, pulse-modulated waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/481—Constructional features, e.g. arrangements of optical elements
- G01S7/4814—Constructional features, e.g. arrangements of optical elements of transmitters alone
- G01S7/4815—Constructional features, e.g. arrangements of optical elements of transmitters alone using multiple transmitters
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Navigation (AREA)
Abstract
The embodiment of the application provides a method and related equipment for detecting LiDAR point cloud data abnormality, wherein the method comprises the following steps: acquiring first position information, wherein the first position information indicates the position of a target data point in LiDAR point cloud data; determining second position information corresponding to the target data point according to the specification of the LiDAR sensor; the target data point is determined to be an outlier or a normal point based on the first location information and the second location information. The technical scheme can efficiently detect abnormal points.
Description
Technical Field
The embodiment of the invention relates to the technical field of information, in particular to a method and related equipment for detecting LiDAR point cloud data anomalies.
Background
Light detection and ranging (light detection and ranging, liDAR) systems are used for mapping, measurement, and object detection, among other uses. LIDAR has many applications including robotic, navigation, autopilot, or other similar applications. The LIDAR system emits laser light and detects reflections in the emitted laser light. By measuring the time-of-flight (TOF) between the emission of the laser light and the detection of the reflected laser light, the distance between the LIDAR unit and the object that reflected the laser light can be calculated.
However, liDAR has a physically executable vulnerability due to technical features. LiDAR emits and receives laser light from LiDAR to surrounding objects. In more detail, a particular object reflects a laser signal from a LiDAR, and the laser signal is returned to a receiver in the LiDAR. An attacker may apply this principle on LiDAR distance measurement to vulnerabilities. Since no attack threat is considered, liDAR receives a duplicate laser signal even if it is an attack on the laser signal. Thus, liDAR point cloud data that is attacked via an attack can lead to false identification of surrounding objects. Under other threats, attack models have been proposed as untrusted machine learning models and deep learning models for object detection by generating resistant objects from point clouds in LiDAR. These vulnerability and attack models are serious threats to driver and pedestrian safety in autopilot. Abnormality detection and intrusion detection methods for LiDAR are required to improve the safety of automatic driving.
Disclosure of Invention
The embodiment of the application provides a method for detecting LiDAR point cloud data anomalies and related equipment. The technical scheme can efficiently detect abnormal points.
According to a first aspect, an embodiment of the present application provides a method for detecting LiDAR point cloud data anomalies, including: acquiring first position information, wherein the first position information indicates the position of a target data point in the LiDAR point cloud data; determining second position information corresponding to the target data point according to the specification of the LiDAR sensor; and determining whether the target data point is an abnormal point or a normal point according to the first position information and the second position information.
It is difficult for an attacker to know all specifications of LiDAR and calculate all points in real time. Therefore, the technical scheme can efficiently detect the abnormal point. Furthermore, the above solution may be a suitable intrusion detection system when used in a limited volume vehicle, because it has a lower computational complexity compared to detection methods of other sensor (e.g. camera, GPS) outputs.
In one possible design, the obtaining the first location information includes: and determining the first position information of the target data point according to the coordinates of the target data point in a Cartesian coordinate system, wherein the first position information comprises an azimuth angle of the target data point and a vertical angle of the target data point.
In one possible design, the specifications of the LiDAR sensor include: horizontal angular resolution, emission interval, number of channels of the LiDAR sensor, vertical angle of each channel, and horizontal angular offset of each channel; the determining, according to the specification of the LiDAR sensor, the second location information corresponding to the target data point includes: determining a plurality of pieces of position information according to the specification of the LiDAR sensor, wherein each piece of position information corresponds to a data point, and each piece of position information comprises an azimuth angle of the corresponding data point and a vertical angle of the corresponding data point; determining the second position information from the plurality of pieces of position information according to the first position information, wherein a difference between an azimuth angle included in the second position information and an azimuth angle included in the first position information is smaller than a difference between an azimuth angle included in any one of the plurality of pieces of position information other than the second position information and an azimuth angle included in the first position information, and a difference between a vertical angle included in the second position information and a vertical angle included in the first position information is smaller than a difference between a vertical angle included in any one of the plurality of pieces of position information other than the second position information and a vertical angle included in the first position information.
In one possible design, the determining that the target data point is an outlier or a normal point based on the first location information and the second location information includes: determining an anomaly score from the first location information and the second location information; determining that the target data point is the outlier or the normal point based on the outlier score.
In one possible design, the determining an anomaly score from the first location information and the second location information includes: determining the anomaly score according to the following formula: s is S anom ＝|α-α near |+|ω-ω near |，S anom Is the anomaly score, alpha is the azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
In one possible design, the determining that the target data point is the outlier or the normal point according to the outlier score includes: when the anomaly score is greater than or equal to a preset threshold, determining that the target data point is the anomaly point; and when the anomaly score is smaller than the preset threshold value, determining that the target data point is the normal point.
According to a second aspect, embodiments of the present application provide an electronic device having functionality to implement the method described in the first aspect. The functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware of the software includes one or more modules corresponding to the functions.
According to a third aspect, embodiments of the present application provide a computer-readable storage medium comprising instructions. When the instructions are run on a computer, the computer is capable of performing the method of the first aspect or any possible implementation of the first aspect.
According to a fourth aspect, there is provided an electronic device comprising a processor and a memory. The processor is connected to the memory. The memory is used for storing instructions, and the processor is used for executing the instructions. The processor, when executing the instructions stored in the memory, is capable of performing the method of the first aspect or any possible implementation of the first aspect.
According to a fifth aspect, there is provided a chip system, wherein the chip system comprises a memory and a processor, wherein the memory is for storing a computer program, and the processor is for calling the computer program from the memory and running the computer program such that a server on which the chip is arranged performs the method of the first aspect or any possible implementation of the first aspect.
According to a sixth aspect, there is provided a computer program product, wherein the electronic device is capable of performing the method of the first aspect or any possible implementation of the first aspect when the computer program product is run on the electronic device.
Drawings
FIG. 1 is a schematic block diagram of a LiDAR scanning system.
FIG. 2 is a schematic block diagram of a LiDAR scanning system according to an embodiment of the present application.
FIG. 3 is a flow chart of an embodiment of a method for detecting LiDAR point cloud data anomalies.
Fig. 4 is a schematic block diagram of an electronic device 400 according to an embodiment of the present application.
Fig. 5 is a schematic block diagram of an electronic device 500 according to an embodiment of the present application.
Detailed Description
The technical scheme of the present application is described below with reference to the accompanying drawings.
FIG. 1 is a schematic block diagram of a LiDAR scanning system.
As shown in fig. 1, the LiDAR scanning system 100 may include at least one LiDAR sensor 101, a preprocessing module 102, and a perception module 103.
The LiDAR scanning system may be coupled to a host system. Host systems may include, but are not limited to, three-dimensional object scanners, vehicle control systems for automated parking assistance, automated driver assistance (e.g., blind spot and collision avoidance), semi-automated or fully automated driving, robotic navigation systems, security cameras, monitoring or surveillance systems, sensor networks for monitoring or surveillance of environmental areas.
LiDAR sensor 101 may include a laser source and a detector subsystem including one or more detectors, such as one or more avalanche photodiodes (avalanche photodiode, APDs), charge-coupled device (CCD) sensors, complementary metal-oxide-semiconductor (CMOS) sensors, or microelectromechanical systems (micro-electro-mechanical system) sensors.
A laser source comprising one or more laser emitters is used to generate and transmit laser light, such as a laser beam. The laser source may generate a gaussian beam. The laser source may transmit a pulsed laser (e.g., a pulsed beam). The laser source typically emits Infrared (IR) light, such as Near Infrared (NIR) light, but may emit one or more types of visible and/or possibly Ultraviolet (UV) light in addition to or instead of infrared light. The laser source may include a plurality of laser emitters, each for transmitting a different type of light. In one example, each of the plurality of laser emitters is configured to transmit infrared light or a respective one of one or more types of visible light. In one example, the plurality of laser emitters includes an infrared laser emitter for transmitting infrared light, a blue laser emitter for transmitting blue light, a red laser emitter for transmitting red light, and a green laser emitter for transmitting green light. The lasers may be controlled to transmit laser beams simultaneously or non-simultaneously.
Those skilled in the art will appreciate that other light sources, such as LEDs, may be suitable for replacing the laser source. However, such an alternative must take into account the system requirements and may be accompanied by additional modifications, such as collimation, to meet the requirements.
The detector subsystem detects the reflected laser light using one or more detectors, generates and outputs a raw data signal corresponding to the received laser light, which is sent to the preprocessing module 102.
The LiDAR sensor may be a single channel LiDAR sensor or a multi-channel LiDAR sensor.
The preprocessing module 102 may be used to receive raw data signals from the LiDAR sensor 101. The raw data signal may include the distance from each point to the LiDAR sensor 101 and the azimuth of each point. The preprocessing module may also be used to convert the raw data signals into LiDAR point cloud data in (x, y, z) format. The values of x, y, z are the projections of the polar coordinates on a cartesian coordinate system. The preprocessing module 102 forwards the LiDAR point cloud data to the perception module 103.
The perception module 103 may be used to determine a distance from the LIDAR scanning system 100 to one or more objects in the environment of the LIDAR scanning system 100, and/or to determine a location and a type of the object.
According to the LiDAR scanning system 100 shown in FIG. 1, an attacker may reside between the preprocessing module 102 and the perception module 103, impersonating itself as the preprocessing module to modify LiDAR point cloud data.
FIG. 2 is a schematic block diagram of a LiDAR scanning system according to an embodiment of the present application.
Compared to the LiDAR scanning system 100 shown in FIG. 1, the LiDAR scanning system 200 shown in FIG. 2 has an added detection module 204.
The function of the LiDAR sensor 202 is similar to that of the LiDAR sensor 101. The function of the preprocessing module 202 is similar to that of the preprocessing module 102, except that the preprocessing module 202 forwards LiDAR point cloud data to the detection module 204 instead of the perception module 203. The detection module 204 may be configured to receive the LiDAR point cloud data from the preprocessing module 202, determine whether a point in the LiDAR point cloud data is a normal point or an abnormal point, and forward the normal point to the sensing module 203. The awareness module 203 may be used to determine the distance from the LiDAR scanning system 200 to one or more objects in the environment of the LiDAR scanning system 200 and/or to determine the location and type of the object.
The detection module 204 may be used to detect whether a point in LiDAR point cloud data has been tampered with or injected by an attacker. In other words, if a point in the LiDAR point cloud data is not determined from the raw data signals acquired by the LiDAR sensor 201 (i.e., an outlier), the detection module 204 may identify the point. This ensures that all points in the LiDAR point cloud data received by the sensing module 203 are determined from the raw data signals acquired by the LiDAR sensors (i.e., normal points).
Alternatively, the detection module 204 may be located within the trust boundary of the perception module 203. This may further ensure the security of the LiDAR scanning system.
The function of the detection module 204 is described below in connection with fig. 3.
FIG. 3 is a flow chart of an embodiment of a method for detecting LiDAR point cloud data anomalies. The method shown in fig. 3 may be performed by the detection module 204.
And 301, acquiring first position information, wherein the first position information indicates the position of a target data point in LiDAR point cloud data.
302, determining second position information corresponding to the target data point according to the specification of the LiDAR sensor.
303, determining that the target data point is an outlier or a normal point based on the first location information and the second location information.
The target data point is any one point in the LiDAR point cloud data.
Optionally, in some embodiments, the first location information may include an azimuth of the target data point and a vertical of the target data point.
As described above, the detection module 204 receives LiDAR point cloud data from the preprocessing module 202. The preprocessing module 202 converts the raw data signals into LiDAR point cloud data in (x, y, z) format. In other words, when the detection module 204 receives LiDAR point cloud data, the detection module 204 obtains coordinates of the target data point in a Cartesian coordinate system. The first location information may be obtained according to the following formula:
(x, y, z) is the coordinates of the target data point in a Cartesian coordinate system, ω is the vertical angle of the target data point, α is the azimuth angle of the target data point, and δ is the horizontal angular offset, which is a predefined constant value. Alpha + delta is the horizontal angle of the target data point. In other words, according to equations 1.1-1.3, the vertical and horizontal angles of the target data point may be obtained, and the azimuth of the target data point may be obtained according to the horizontal angle and predefined horizontal angle offset of the target data point.
Optionally, in some embodiments, determining the second location information corresponding to the target data point according to the specification of the LiDAR sensor includes: determining a plurality of pieces of position information according to the specification of the LiDAR sensor, wherein each piece of position information corresponds to a data point, and each piece of position information comprises an azimuth angle of the corresponding data point and a vertical angle of the corresponding data point; and determining second position information from the plurality of pieces of position information according to the first position information, wherein a difference between an azimuth angle included in the second position information and an azimuth angle included in the first position information is smaller than a difference between an azimuth angle included in any one of the plurality of pieces of position information other than the second position information and an azimuth angle included in the first position information, and a difference between a vertical angle included in the second position information and a vertical angle included in the first position information is smaller than a difference between a vertical angle included in any one of the plurality of pieces of position information other than the second position information and a vertical angle included in the first position information.
The specifications of the LiDAR sensor include: horizontal angular resolution, emission spacing, number of channels of the LiDAR sensor, vertical angle of each channel, and horizontal angular offset of each channel.
The horizontal angular resolution, emission interval, and number of channels of the LiDAR sensor determine the number of possible horizontal and vertical angle pairs. The possible values of azimuth per frame may be determined from the horizontal angular resolution and the transmission interval. Specifically, the quotient of the horizontal angular resolution and the transmission interval is a possible value of the azimuth angle per frame. If the quotient of the horizontal angular resolution and the emission interval is not an integer, the quotient may be rounded down/up/rounded down to obtain the possible value. For each azimuth, the number of channels of the LiDAR sensor is the number of possible horizontal and vertical angle pairs. The value of the vertical angle in each horizontal-vertical angle pair may be determined from the vertical angle of the corresponding channel. The value of the horizontal angle of each horizontal-vertical angle pair may be determined according to the horizontal angle resolution, and the value of the azimuth angle corresponding to each horizontal-vertical angle pair may be determined according to the horizontal angle of each horizontal-vertical angle pair and the horizontal angle offset of the corresponding channel. For example, the azimuth angle may be determined according to the following equation:
is the horizontal angle in the ith horizontal-vertical angle pair in the frame, which corresponds to the jth channel, delta, of the LiDAR sensor i Is the horizontal angular offset of the jth channel, alpha i Is the azimuth corresponding to the i-th horizontal-vertical angle pair.
Assuming a single return mode 32 channel LiDAR sensor, the emission interval is 55.52 microseconds and the horizontal angular resolution is 10Hz. For each frame there are about 1801 (=10 Hz/55.52 microseconds) possible values of azimuth. For each azimuth there are 32 possible horizontal and vertical angle pairs. The 32 possible pairs of horizontal and vertical angles are in one-to-one correspondence with the 32 channels of the LiDAR sensor. There are 1801 x 32 horizontal-vertical angle pairs per frame. Thus, there is 1801×32 pieces of position information. 1801×32 pieces of position information are in one-to-one correspondence with 1801×32 horizontal-vertical angle pairs. Each positional information includes an azimuth angle and a vertical angle of a corresponding horizontal-vertical angle pair, wherein the azimuth angle of the corresponding horizontal-vertical angle pair can be determined according to equation 1.4. The second location information is one of 1801×32 pieces of location information. The process of finding the second location in 1801×32 pieces of location information may be performed quickly by binary search or parallel operation.
Optionally, in some embodiments, determining that the target data point is an outlier or a normal point based on the first location information and the second location information includes: determining an anomaly score based on the first location information and the second location information; the target data point is determined to be an outlier or a normal point based on the outlier score.
Optionally, in some embodiments, determining the anomaly score from the first location information and the second location information includes: the anomaly score is determined according to the following formula:
S anom ＝|α-α near |+|ω-ω near i, (equation 1.5)
S anom Is an anomaly score, alpha is an azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
Optionally, in some embodiments, determining the anomaly score from the first location information and the second location information includes: the anomaly score is determined according to the following formula:
S anom is an anomaly score, alpha is an azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
Optionally, in some embodiments, determining the anomaly score from the first location information and the second location information includes: the anomaly score is determined according to the following formula:
S anom ＝|α-α near i, (equation 1.7)
S anom Is an anomaly score, alpha is an azimuth angle included in the first position information, alpha near Is the azimuth included in the second location information. In this case, the first location information may include only the azimuth of the target data point. Accordingly, the second location information may be location information including an azimuth nearest to the target data point.
Optionally, in some embodiments, determining that the target data point is an outlier or a normal point based on the outlier score comprises: when the anomaly score is greater than or equal to a preset threshold, determining the target data point as an anomaly point; when the anomaly score is less than a preset threshold, the target data point is determined to be a normal point.
Further, if the target data point is a normal point, the target data point may be forwarded to the perception module 203. If the target data point is an outlier, the target data point may be discarded.
It is difficult for an attacker to know all specifications of LiDAR and calculate all points in real time. The present application can detect attacks without delay by performing relatively low computational operations. Meanwhile, the method and the device can be used with other intrusion detection systems at or behind the sensing module, so that the detection rate can be improved. Furthermore, the present application may be a suitable intrusion detection system when used in a limited volume vehicle, because it has a lower computational complexity than detection methods of other sensor (e.g., camera, GPS) outputs.
Alternatively, the detection module for performing the method shown in fig. 3 may be located within the trust boundary of the perception module to detect such attacks.
Fig. 4 is a schematic block diagram of an electronic device 400 according to an embodiment of the present application. As shown in fig. 4, the electronic device 400 includes: an acquisition module 401 and a determination module 402.
The obtaining module 401 is configured to obtain first location information, where the first location information indicates a location of a target data point in the LiDAR point cloud data.
The determining module 402 is configured to determine second location information corresponding to the target data point according to the specification of the LiDAR sensor.
The determination module 402 is further configured to determine whether the target data point is an outlier or a normal point based on the first location information and the second location information.
Optionally, the obtaining module 401 is specifically configured to: first position information of the target data point is determined according to coordinates of the target data point in a Cartesian coordinate system, wherein the first position information comprises an azimuth angle of the target data point and a vertical angle of the target data point.
Optionally, the specifications of the LiDAR sensor include: horizontal angular resolution, emission interval, number of channels of the LiDAR sensor, vertical angle of each channel, and horizontal angular offset of each channel; the determining module 402 is specifically configured to: determining a plurality of pieces of position information according to the specification of the LiDAR sensor, wherein each piece of position information corresponds to a data point, and each piece of position information comprises an azimuth angle of the corresponding data point and a vertical angle of the corresponding data point; and determining second position information from the plurality of pieces of position information according to the first position information, wherein a difference between an azimuth angle included in the second position information and an azimuth angle included in the first position information is smaller than a difference between an azimuth angle included in any one of the plurality of pieces of position information other than the second position information and an azimuth angle included in the first position information, and a difference between a vertical angle included in the second position information and a vertical angle included in the first position information is smaller than a difference between a vertical angle included in any one of the plurality of pieces of position information other than the second position information and a vertical angle included in the first position information.
Optionally, the determining module 402 is specifically configured to: determining an anomaly score based on the first location information and the second location information; the target data point is determined to be an outlier or a normal point based on the outlier score.
Optionally, the determining module 402 is specifically configured to determine the anomaly score according to the following formula:
S anom ＝|α-α near |+|ω-ω near |
S anom is an anomaly score, alpha is an azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
Optionally, the determining module 402 is specifically configured to: when the anomaly score is greater than or equal to a preset threshold, determining that the target data point is an anomaly point; when the anomaly score is less than a preset threshold, the target data point is determined to be a normal point.
Fig. 5 is a schematic block diagram of an electronic device 500 according to an embodiment of the present application.
As shown in fig. 5, an electronic device 500 may include a transceiver 501, a processor 502, and a memory 503. Memory 503 may be used to store code, instructions, etc. that are executed by processor 502.
It should be appreciated that the processor 502 may be an integrated circuit chip and have signal processing capabilities. In implementation, the steps of the above-described method embodiments may be accomplished through the use of hardware integrated logic circuits in a processor or through the use of instructions in the form of software. The processor may be a general purpose processor, a digital signal processor (digital signal processor, DSP), an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field programmable gate array, FPGA) or another programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The processor may implement or perform the methods, steps and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor, or the processor may be any conventional processor or the like. The steps of the methods disclosed with reference to embodiments of the present invention may be performed and performed directly by a hardware decoding processor or may be performed and performed using a combination of hardware and software modules in a decoding processor. The software modules may be located in a storage medium well known in the art, such as random access memory, flash memory, read only memory, programmable read only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory and the processor reads the information in the memory and performs the steps of the method described above in conjunction with the hardware in the processor.
It will be appreciated that the memory 503 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) and acts as external cache. By way of example, and not limitation, many forms of RAM may be used, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DR RAM).
It should be noted that the memories in the systems and methods described in this specification include, but are not limited to, these memories and any other suitable type of memory.
Embodiments of the present application also provide a system chip, wherein the system chip includes an input/output interface, at least one processor, at least one memory, and a bus. The at least one memory is configured to store instructions, and the at least one processor is configured to invoke the instructions of the at least one memory to perform the operations of the methods of the embodiments described above.
Embodiments of the present application also provide a computer storage medium that may store program instructions for performing any of the methods described above.
Alternatively, the storage medium may specifically be the memory 503.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether a function is performed by hardware or software depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may use different methods for each particular application to achieve the described functionality, but such implementation should not be considered to be beyond the scope of this application.
It will be apparent to those skilled in the art that for the purposes of convenience and brevity of description, reference will be made to the corresponding processes in the above-described method embodiments for the specific operation of the aforementioned systems, devices and units. And will not be described in detail herein.
In several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely examples. For example, the cell division is just one logical functional division, and other divisions are possible in practical implementations. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Furthermore, the coupling or direct coupling or communication connection shown or discussed with each other may be implemented using some interface. An indirect coupling or communication connection between devices or elements may be implemented in electronic, mechanical, or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
When the functions are implemented in the form of software functional units and sold or used as a stand-alone product, the functions may be stored in a computer-readable storage medium. Based on such understanding, the technical solutions in the present application are essentially either parts contributing to the prior art or some technical solutions may be implemented in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for instructing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or some of the steps of the method described in the embodiments of the present application. The storage medium includes: any medium that can store program code, such as a USB flash drive, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk.
The above description is merely a specific implementation of the present application and is not intended to limit the scope of the present application. Any changes or substitutions that would be obvious to one skilled in the art within the scope of the present disclosure are intended to be within the scope of the present disclosure. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (15)
1. A method for detecting LiDAR point cloud data anomalies, comprising:
acquiring first position information, wherein the first position information indicates the position of a target data point in the LiDAR point cloud data;
determining second position information corresponding to the target data point according to the specification of the LiDAR sensor;
and determining whether the target data point is an abnormal point or a normal point according to the first position information and the second position information.
2. The method of claim 1, wherein the acquiring the first location information comprises:
and determining the first position information of the target data point according to the coordinates of the target data point in a Cartesian coordinate system, wherein the first position information comprises an azimuth angle of the target data point and a vertical angle of the target data point.
3. The method of claim 2, wherein the specification of the LiDAR sensor comprises: horizontal angular resolution, emission interval, number of channels of the LiDAR sensor, vertical angle of each channel, and horizontal angular offset of each channel;
the determining, according to the specification of the LiDAR sensor, the second location information corresponding to the target data point includes:
determining a plurality of pieces of position information according to the specification of the LiDAR sensor, wherein each piece of position information corresponds to a data point, and each piece of position information comprises an azimuth angle of the corresponding data point and a vertical angle of the corresponding data point;
determining the second position information from the plurality of pieces of position information according to the first position information, wherein a difference between an azimuth angle included in the second position information and an azimuth angle included in the first position information is smaller than a difference between an azimuth angle included in any one of the plurality of pieces of position information other than the second position information and an azimuth angle included in the first position information, and a difference between a vertical angle included in the second position information and a vertical angle included in the first position information is smaller than a difference between a vertical angle included in any one of the plurality of pieces of position information other than the second position information and a vertical angle included in the first position information.
4. The method of claim 3, wherein the determining that the target data point is an outlier or a normal point from the first location information and the second location information comprises:
determining an anomaly score from the first location information and the second location information;
determining that the target data point is the outlier or the normal point based on the outlier score.
5. The method of claim 4, wherein the determining an anomaly score from the first location information and the second location information comprises:
determining the anomaly score according to the following formula:
S anom ＝|α-α near |+|ω-ω near |，
S anom is the anomaly score, alpha is the azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
6. The method of claim 4 or 5, wherein the determining that the target data point is the outlier or the normal point according to the outlier score comprises:
when the anomaly score is greater than or equal to a preset threshold, determining that the target data point is the anomaly point;
and when the anomaly score is smaller than the preset threshold value, determining that the target data point is the normal point.
7. An electronic device, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring first position information, wherein the first position information indicates the position of a target data point in LiDAR point cloud data;
the determining module is used for determining second position information corresponding to the target data point according to the specification of the LiDAR sensor;
the determining module is further configured to determine whether the target data point is an outlier or a normal point according to the first location information and the second location information.
8. The electronic device of claim 7, wherein the acquisition module is specifically configured to: and determining the first position information of the target data point according to the coordinates of the target data point in a Cartesian coordinate system, wherein the first position information comprises an azimuth angle of the target data point and a vertical angle of the target data point.
9. The electronic device of claim 8, wherein the specification of the LiDAR sensor comprises: horizontal angular resolution, emission interval, number of channels of the LiDAR sensor, vertical angle of each channel, and horizontal angular offset of each channel;
the determining module is specifically configured to:
determining a plurality of pieces of position information according to the specification of the LiDAR sensor, wherein each piece of position information corresponds to a data point, and each piece of position information comprises an azimuth angle of the corresponding data point and a vertical angle of the corresponding data point;
determining the second position information from the plurality of pieces of position information according to the first position information, wherein a difference between an azimuth angle included in the second position information and an azimuth angle included in the first position information is smaller than a difference between an azimuth angle included in any one of the plurality of pieces of position information other than the second position information and an azimuth angle included in the first position information, and a difference between a vertical angle included in the second position information and a vertical angle included in the first position information is smaller than a difference between a vertical angle included in any one of the plurality of pieces of position information other than the second position information and a vertical angle included in the first position information.
10. The electronic device of claim 9, wherein the determining module is specifically configured to:
determining an anomaly score from the first location information and the second location information;
determining that the target data point is the outlier or the normal point based on the outlier score.
11. The electronic device of claim 10, wherein the determining module is specifically configured to determine the anomaly score according to the following formula:
S anom ＝|α-α near |+|ω-ω near |，
S anom is the anomaly score, alpha is the azimuth angle included in the first position information, alpha near Is the azimuth angle included in the second position information, ω is the vertical angle included in the first position information, and ω near Is the vertical angle included in the second position information.
12. The electronic device according to claim 10 or 11, wherein the determining module is specifically configured to:
when the anomaly score is greater than or equal to a preset threshold, determining that the target data point is the anomaly point;
and when the anomaly score is smaller than the preset threshold value, determining that the target data point is the normal point.
13. A computer readable storage medium storing instructions which, when run on a computer, are capable of performing the method of any one of claims 1 to 6.
14. An electronic device comprising a memory and a processor, wherein the memory is for storing a computer program and the processor is for calling the computer program from the memory and running the computer program such that a computer on which the chip is arranged performs the method according to any of claims 1 to 6.
15. A computer program product, wherein the computer is capable of performing the method according to any of claims 1 to 6 when the computer program product is run on a computer.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/114368 WO2023023951A1 (en) | 2021-08-24 | 2021-08-24 | Method for detecting anomalies of lidar point cloud data and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117730265A true CN117730265A (en) | 2024-03-19 |
Family
ID=85321583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202180100860.0A Pending CN117730265A (en) | 2021-08-24 | 2021-08-24 | Method for detecting LiDAR point cloud data abnormality and related equipment |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4363888A1 (en) |
| CN (1) | CN117730265A (en) |
| WO (1) | WO2023023951A1 (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109285188B (en) * | 2017-07-21 | 2020-04-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating position information of target object |
| CN108226894A (en) * | 2017-11-29 | 2018-06-29 | 北京数字绿土科技有限公司 | A kind of Processing Method of Point-clouds and device |
| CN110007315A (en) * | 2019-04-09 | 2019-07-12 | 深圳市速腾聚创科技有限公司 | Laser radar detection device, detection method and control system |
| US11543535B2 (en) * | 2019-07-03 | 2023-01-03 | Uatc, Llc | Lidar fault detection system |
-
2021
- 2021-08-24 CN CN202180100860.0A patent/CN117730265A/en active Pending
- 2021-08-24 EP EP21954494.7A patent/EP4363888A1/en active Pending
- 2021-08-24 WO PCT/CN2021/114368 patent/WO2023023951A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| EP4363888A1 (en) | 2024-05-08 |
| WO2023023951A1 (en) | 2023-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10613203B1 (en) | Interference mitigation for light detection and ranging | |
| US10614322B2 (en) | Object recognition device | |
| US10509111B2 (en) | LIDAR sensor device | |
| CN109782258B (en) | Position detection method and device for vehicle laser radar and storage medium | |
| KR20200100103A (en) | Systems and methods for improving detection of feedback signals in optical ranging and detection systems | |
| CA2772402A1 (en) | Vehicular ranging system and method of operation | |
| CN109923437B (en) | Laser radar system | |
| JP5540217B2 (en) | Laser scan sensor | |
| EP3279691B1 (en) | Rangefinder based on parallax calculation | |
| KR20230003089A (en) | LiDAR system with fog detection and adaptive response | |
| CN115047472B (en) | Method, device, equipment and storage medium for determining laser radar point cloud layering | |
| JP6186863B2 (en) | Ranging device and program | |
| US11619725B1 (en) | Method and device for the recognition of blooming in a lidar measurement | |
| CN109031333B (en) | Distance measuring method and device, storage medium, and electronic device | |
| US10830887B2 (en) | Object sensor assembly including stereoscopic cameras and range finders | |
| CN117730265A (en) | Method for detecting LiDAR point cloud data abnormality and related equipment | |
| US20230090576A1 (en) | Dynamic control and configuration of autonomous navigation systems | |
| US20220326364A1 (en) | Method for operating a lidar system | |
| JP2009276248A (en) | Laser radar device | |
| CN115184946A (en) | Radar-based distance detection method and device, radar and terminal | |
| KR20220048196A (en) | Apparatus for LIDAR | |
| WO2023220977A1 (en) | Method and device for detecting data | |
| JP2019007892A (en) | Information acquisition device, program, and information acquisition system | |
| KR102176700B1 (en) | An Apparatus and A Method For Lidar Time Of Flight measurement | |
| CN118131173A (en) | Radar signal processing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |